CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

set-up-your-fork

Turn on the GitHub features a fork of the carnival needs (Issues, Actions and GitHub Pages) using the GitHub CLI, lock the fork down so only its owner can open issues, comment and open pull requests, then deploy the carnival and share its link. Use when someone asks to set up their fork, turn on issues or Pages, lock down their fork, get a shareable link to their carnival, or when the Issues tab, CI checks or the Pages deploy are missing on a fork.

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tightly written, fully executable runbook: concrete `gh` commands with error branches, pre-flight and post-check validation, and a clear summary/fallback structure. The only deductions are a slightly expository intro, a leftover TODO comment, and a 125-line monolith whose manual-steps section could be split into a reference file.

Suggestions

Resolve and remove the TODO comment in section 3 ('confirm the interaction lock doesn't stop the Tessl GitHub App or Tessl Review…') — an unresolved developer note in the instruction body adds tokens without executable value; fold the confirmed behavior into the step text.

Trim the intro's per-feature rationale ('so they can file the starter issues and label them', 'so they can play and share their carnival online…') to a one-line statement of the three features; the operational details already appear in the steps and summary.

Consider moving the 'Manual steps' fallback into a small reference file (e.g. references/manual-steps.md) referenced from section 1 and the failure branches, keeping SKILL.md as a leaner overview.

DimensionReasoningScore

Conciseness

The body is command-driven with tight guardrails and almost no filler — 'Run `gh auth status`. If `gh` isn't installed or isn't logged in, stop…' — but the intro spends several lines explaining why Issues/Actions/Pages matter, and an unresolved developer TODO ('<!-- TODO: confirm the interaction lock doesn't stop the Tessl GitHub App… -->') occupies tokens that earn nothing at execution time. This is the 4 anchor (efficient, minor trims possible) rather than 5 ('every token earns its place').

4 / 5

Actionability

Every step is a copy-paste-ready `gh` command — `gh repo edit OWNER/REPO --enable-issues`, `gh api -X PUT repos/OWNER/REPO/interaction-limits -f limit=collaborators_only -f expiry=six_months`, `gh workflow run pages.yml --repo OWNER/REPO --ref main` — with concrete failure branches ('If that says Pages already exists, switch it…', 'If GitHub answers 409…') and a complete manual fallback section. Fully executable, matching the 5 anchor.

5 / 5

Workflow Clarity

The sequence is explicit with real validation checkpoints and feedback loops: pre-flight checks (`gh repo view OWNER/REPO --json isFork,viewerPermission`, the upstream-repo guard), post-checks (`--jq .approval_policy`, noting `expires_at`), deploy monitoring (`gh run watch <run id>`), and error recovery on every branch ('keep going if one fails: note it for the summary'). This is the 5 anchor; the 4 anchor ('most checkpoints present') undersells the coverage.

5 / 5

Progressive Disclosure

No bundle files exist, and the single SKILL.md is cleanly sectioned (prerequisites → enable → lock → deploy → summarize → manual steps) with no nested references, which clears the 3 anchor ('some structure… references not clearly signaled'). It lands at 4 rather than 5 because at ~125 lines it is a monolithic runbook whose 'Manual steps' fallback is separable content that could live in a reference file.

4 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: concrete third-person action list, explicit and varied 'Use when…' triggers including failure symptoms (missing Issues tab, CI checks, Pages deploy), and a clearly bounded carnival-fork niche. No fluff, over-claims, or trigger ambiguity.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Turn on the GitHub features a fork of the carnival needs (Issues, Actions and GitHub Pages) using the GitHub CLI', 'lock the fork down so only its owner can open issues, comment and open pull requests', 'deploy the carnival and share its link' — covering the skill's full scope. It matches the 5 anchor (comprehensive concrete actions) rather than 4, since no meaningful capability of the skill is left out.

5 / 5

Completeness

It explicitly answers both 'what' (enable Issues/Actions/Pages via the GitHub CLI, lock down interactions, deploy and share the link) and 'when' via a concrete 'Use when…' clause with multiple trigger phrases. This mirrors the 5 anchor exactly; the 4 anchor applies only when the 'when' is less explicit.

5 / 5

Trigger Term Quality

Trigger phrasing is comprehensive and natural: 'set up their fork', 'turn on issues or Pages', 'lock down their fork', 'get a shareable link to their carnival', plus symptom-based triggers ('Issues tab, CI checks or the Pages deploy are missing on a fork'). These are the phrases a user would actually say; no common variation is identifiable as missing, so it fits the 5 anchor over the 4 ('a few natural terms missing').

5 / 5

Distinctiveness Conflict Risk

The niche is distinct — setting up 'a fork of the carnival' with carnival/fork/Pages-specific triggers — so it is unlikely to fire for unrelated skills. It fits the 5 anchor ('clear niche with distinct triggers; minimal conflict risk') rather than 4, which requires noticeable overlap with closely related skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

hamzaoza/carnival-lock-test

Path

skills/set-up-your-fork/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.